© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12932
    Prev
    Next
    INDEX
    Explanations

    numerical representations and terms related to data and counting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.51
    Pfalz
    -0.50
    ensement
    -0.50
    TypedDataSet
    -0.48
    Hochspringen
    -0.48
    MeasureSpec
    -0.47
    StoryboardSegue
    -0.46
    Xna
    -0.46
     bacon
    -0.45
    CloseOperation
    -0.44
    POSITIVE LOGITS
    ſelf
    0.43
    indo
    0.41
    wed
    0.36
    hydration
    0.35
     Madura
    0.35
     Sixth
    0.34
    unshift
    0.34
     Astro
    0.34
    nese
    0.34
    strftime
    0.34
    Activations Density 0.505%

    No Known Activations